def ssd_multibox_layer(inputs,
num_classes,
sizes,
ratios=[1],
normalization=-1,
bn_normalization=False):
"""Construct a multibox layer, return a class and localization predictions.
"""
net = inputs
if normalization > 0:
net = custom_layers.l2_normalization(net, scaling=True)
# Number of anchors.
num_anchors = len(sizes) + len(ratios)
# Location.
num_loc_pred = num_anchors * 4
loc_pred = slim.conv2d(net,
num_loc_pred, [3, 3],
activation_fn=None,
scope='conv_loc')
loc_pred = custom_layers.channel_to_last(loc_pred)
loc_pred = tf.reshape(loc_pred,
tensor_shape(loc_pred, 4)[:-1] + [num_anchors, 4])
# Class prediction.
num_cls_pred = num_anchors * num_classes
cls_pred = slim.conv2d(net,
num_cls_pred, [3, 3],
activation_fn=None,
scope='conv_cls')
cls_pred = custom_layers.channel_to_last(cls_pred)
cls_pred = tf.reshape(
cls_pred,
tensor_shape(cls_pred, 4)[:-1] + [num_anchors, num_classes])
return cls_pred, loc_pred
def ssd_multibox_layer(
inputs, # Feature maps
num_classes,
ratios=[1], # Default H:W = 1:1
normalization=-1):
"""
Construct a multibox layer, return a class and localization predictions.
:param inputs:
:param num_classes:
:param ratios:
:param normalization:
:return: the class and localization prediction
"""
net = inputs
if normalization > 0:
net = custom_layers.l2_normalization(net)
# Number of anchors
num_anchors = len(ratios) + 2
# Location: each anchor has 4 location
num_loc_pred = num_anchors * 4
# Have a 3x3 conv on feature map to get location prediction, and the number of location prediction is num_loc_pred
loc_pred = slim.conv2d(net,
num_loc_pred, [3, 3],
activation_fn=None,
scope='conv_loc')
loc_shape = [tf.shape(loc_pred)[0]
] + loc_pred.get_shape().as_list()[1:3] + [num_anchors, 4]
loc_pred = tf.reshape(loc_pred, loc_shape)
# Class prediction : each anchor has 2 classifaction
num_cls_pred = num_anchors * num_classes
cls_pred = slim.conv2d(net,
num_cls_pred, [3, 3],
activation_fn=None,
scope='conv_cls')
cls_shape = [
tf.shape(cls_pred)[0]
] + cls_pred.get_shape().as_list()[1:3] + [num_anchors, num_classes]
cls_pred = tf.reshape(cls_pred, cls_shape)
return cls_pred, loc_pred